Phase structures-based hybrid approaches for defect detection in vials
Bibliographic record
Abstract
Quality control and assurance in pharmaceutical vial manufacturing are paramount to ensure drug safety and efficacy. Defects such as cracks, bubbles, black spots, and wrinkles can compromise product quality and patient safety. This study proposes a novel methodology that integrates fast non-local means (FNLM) filtering with hybrid image processing techniques to detect these defects. Previous approaches have often struggled with subtle anomalies in texture and surface features. The proposed solution leverages phase structure analysis, utilizing phase stretch transform (PST) to effectively highlight subtle anomalies by extracting features sensitive to phase variations. These features are further refined using Gaussian filtering, with Otsu thresholding applied for precise segmentation and defect boundary identification. Morphological dilation enhances detection speed and accuracy, while region of interest (ROI) identification aids in localizing defects and facilitating decision-making. The system demonstrates significant improvements in quality control, achieving high performance metrics: precision (98.85%), recall (98.57%), accuracy (98.36%), specificity (98.0%), and F1-score (98.71%). It also achieves impressive AUC-ROC (98.18%) and AUC-PR (99.08%) values, demonstrating its robustness and suitability for defect detection in pharmaceutical vials.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".